Can Open-Source LLMs Compete With Proprietary Ones for Complex Diagnoses?

episode

JAMA+ AI Conversations not yet transcribed

▲ 0

Transcript

This episode hasn't been transcribed yet Upvotes decide what gets transcribed next — 0 so far. Sign in to upvote

Related

recent transcribed audio

Obsolete or Irreplaceable? Garrison Lovely on Stopping the Race to Replace Human Labor 2h 13m · 29 Sep 2026 · "The Cognitive Revolution"

Mission: Impossible 47 min · 29 Sep 2026 · I've Had It

THE DISCLAIMER: Summer Wardrobe Planning 12 min · 29 Sep 2026 · The Hauraki Big Show

Squiz Shortcuts: What’s an AI agent? 12 min · 29 Sep 2026 · Squiz Today

FULL SHOW: The Big Show Travel Guide 57 min · 29 Sep 2026 · The Hauraki Big Show

LVST 29 de septiembre de 2026 1h 10m · 29 Sep 2026 · La Venganza Será Terrible (oficial)

Report any issue

Source

Recorded04 Apr 2025

Publisherfeeds.libsyn.com ↗

Handlerec:14210667

Show notes

A recent study published in JAMA Health Forum suggests that institutions may be able to deploy custom open-source large language models (LLMs) that run locally without sacrificing data privacy or flexibility. Coauthors Thomas A. Buckley, BS, and Arjun K. Manrai, PhD, from the Department of Biomedical Informatics at Harvard Medical School join JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss. Related Content: Can Open-Source AI Models Diagnose Complex Cases as Well as GPT-4?

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Sign in